© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1933
    Prev
    Next
    INDEX
    Explanations

    visible pores, face, redness, loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Futures
    -0.10
    åĻ¨æĿIJ
    -0.09
    åīįä¸ī
    -0.09
    æ³°
    -0.08
    олоÑģ
    -0.08
    raig
    -0.08
    æ³°å±±
    -0.08
    è¡Įãģį
    -0.08
    ÑĢова
    -0.08
     fancy
    -0.08
    POSITIVE LOGITS
    大éĿ¢ç§¯
    0.10
    çªģåĩºéĹ®é¢ĺ
    0.10
    ori
    0.09
    åºķæ°Ķ
    0.09
    holes
    0.09
    çijķçĸµ
    0.09
    è¡Ķæİ¥
    0.09
    ANEL
    0.09
    çĸ¤çĹķ
    0.08
    ç¬ı
    0.08
    Activations Density 0.037%

    No Known Activations